Attending to Topological Spaces: The Cellular Transformer

Na minha lista:
Detalhes bibliográficos
Publicado no:arXiv.org (May 23, 2024), p. n/a
Autor principal: Ballester, Rubén
Outros Autores: Hernández-García, Pablo, Papillon, Mathilde, Battiloro, Claudio, Miolane, Nina, Birdal, Tolga, Casacuberta, Carles, Escalera, Sergio, Hajij, Mustafa
Publicado em:
Cornell University Library, arXiv.org
Assuntos:
Acesso em linha:Citation/Abstract
Full text outside of ProQuest
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!

MARC

LEADER 00000nab a2200000uu 4500
001 3059654581
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3059654581 
045 0 |b d20240523 
100 1 |a Ballester, Rubén 
245 1 |a Attending to Topological Spaces: The Cellular Transformer 
260 |b Cornell University Library, arXiv.org  |c May 23, 2024 
513 |a Working Paper 
520 3 |a Topological Deep Learning seeks to enhance the predictive performance of neural network models by harnessing topological structures in input data. Topological neural networks operate on spaces such as cell complexes and hypergraphs, that can be seen as generalizations of graphs. In this work, we introduce the Cellular Transformer (CT), a novel architecture that generalizes graph-based transformers to cell complexes. First, we propose a new formulation of the usual self- and cross-attention mechanisms, tailored to leverage incidence relations in cell complexes, e.g., edge-face and node-edge relations. Additionally, we propose a set of topological positional encodings specifically designed for cell complexes. By transforming three graph datasets into cell complex datasets, our experiments reveal that CT not only achieves state-of-the-art performance, but it does so without the need for more complex enhancements such as virtual nodes, in-domain structural encodings, or graph rewiring. 
653 |a Datasets 
653 |a Neural networks 
653 |a Performance prediction 
653 |a Transformers 
653 |a Topology 
700 1 |a Hernández-García, Pablo 
700 1 |a Papillon, Mathilde 
700 1 |a Battiloro, Claudio 
700 1 |a Miolane, Nina 
700 1 |a Birdal, Tolga 
700 1 |a Casacuberta, Carles 
700 1 |a Escalera, Sergio 
700 1 |a Hajij, Mustafa 
773 0 |t arXiv.org  |g (May 23, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3059654581/abstract/embedded/J7RWLIQ9I3C9JK51?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2405.14094